Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer
Background and objectiveAccurately predicting the extent of lung tumor infiltration is crucial for improving patient survival and cure rates. This study aims to evaluate the application value of an improved CT index combined with serum biomarkers, obtained through an artificial intelligence recognit...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2024-04-01
|
Series: | Frontiers in Public Health |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2024.1368217/full |
_version_ | 1797221296623321088 |
---|---|
author | Leyuan Meng Ping Zhu Ping Zhu Kaijian Xia Kaijian Xia |
author_facet | Leyuan Meng Ping Zhu Ping Zhu Kaijian Xia Kaijian Xia |
author_sort | Leyuan Meng |
collection | DOAJ |
description | Background and objectiveAccurately predicting the extent of lung tumor infiltration is crucial for improving patient survival and cure rates. This study aims to evaluate the application value of an improved CT index combined with serum biomarkers, obtained through an artificial intelligence recognition system analyzing CT features of pulmonary nodules, in early prediction of lung cancer infiltration using machine learning models.Patients and methodsA retrospective analysis was conducted on clinical data of 803 patients hospitalized for lung cancer treatment from January 2020 to December 2023 at two hospitals: Hospital 1 (Affiliated Changshu Hospital of Soochow University) and Hospital 2 (Nantong Eighth People’s Hospital). Data from Hospital 1 were used for internal training, while data from Hospital 2 were used for external validation. Five algorithms, including traditional logistic regression (LR) and machine learning techniques (generalized linear models [GLM], random forest [RF], gradient boosting machine [GBM], deep neural network [DL], and naive Bayes [NB]), were employed to construct models predicting early lung cancer infiltration and were analyzed. The models were comprehensively evaluated through receiver operating characteristic curve (AUC) analysis based on LR, calibration curves, decision curve analysis (DCA), as well as global and individual interpretative analyses using variable feature importance and SHapley additive explanations (SHAP) plots.ResultsA total of 560 patients were used for model development in the training dataset, while a dataset comprising 243 patients was used for external validation. The GBM model exhibited the best performance among the five algorithms, with AUCs of 0.931 and 0.99 in the validation and test sets, respectively, and accuracies of 0.857 and 0.955 in the validation and test groups, respectively, outperforming other models. Additionally, the study found that nodule diameter and average CT value were the most significant features for predicting lung cancer infiltration using machine learning models.ConclusionThe GBM model established in this study can effectively predict the risk of infiltration in early-stage lung cancer patients, thereby improving the accuracy of lung cancer screening and facilitating timely intervention for infiltrative lung cancer patients by clinicians, leading to early diagnosis and treatment of lung cancer, and ultimately reducing lung cancer-related mortality. |
first_indexed | 2024-04-24T13:03:11Z |
format | Article |
id | doaj.art-9b2c2c905d6f4e5d8a17cdba4a9a0e5e |
institution | Directory Open Access Journal |
issn | 2296-2565 |
language | English |
last_indexed | 2024-04-24T13:03:11Z |
publishDate | 2024-04-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Public Health |
spelling | doaj.art-9b2c2c905d6f4e5d8a17cdba4a9a0e5e2024-04-05T09:45:54ZengFrontiers Media S.A.Frontiers in Public Health2296-25652024-04-011210.3389/fpubh.2024.13682171368217Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancerLeyuan Meng0Ping Zhu1Ping Zhu2Kaijian Xia3Kaijian Xia4Department of Respiratory and Critical Care Medicine, Affiliated Hospital of Nantong University, Medical School of Nantong University, Jiangsu, Nantong, ChinaDepartment of Scientific Research, The Changshu Affiliated Hospital of Soochow University, Jiangsu, Suzhou, ChinaChangshu Key Laboratory of Medical Artificial Intelligence and Big Data, Jiangsu, Suzhou, ChinaDepartment of Scientific Research, The Changshu Affiliated Hospital of Soochow University, Jiangsu, Suzhou, ChinaChangshu Key Laboratory of Medical Artificial Intelligence and Big Data, Jiangsu, Suzhou, ChinaBackground and objectiveAccurately predicting the extent of lung tumor infiltration is crucial for improving patient survival and cure rates. This study aims to evaluate the application value of an improved CT index combined with serum biomarkers, obtained through an artificial intelligence recognition system analyzing CT features of pulmonary nodules, in early prediction of lung cancer infiltration using machine learning models.Patients and methodsA retrospective analysis was conducted on clinical data of 803 patients hospitalized for lung cancer treatment from January 2020 to December 2023 at two hospitals: Hospital 1 (Affiliated Changshu Hospital of Soochow University) and Hospital 2 (Nantong Eighth People’s Hospital). Data from Hospital 1 were used for internal training, while data from Hospital 2 were used for external validation. Five algorithms, including traditional logistic regression (LR) and machine learning techniques (generalized linear models [GLM], random forest [RF], gradient boosting machine [GBM], deep neural network [DL], and naive Bayes [NB]), were employed to construct models predicting early lung cancer infiltration and were analyzed. The models were comprehensively evaluated through receiver operating characteristic curve (AUC) analysis based on LR, calibration curves, decision curve analysis (DCA), as well as global and individual interpretative analyses using variable feature importance and SHapley additive explanations (SHAP) plots.ResultsA total of 560 patients were used for model development in the training dataset, while a dataset comprising 243 patients was used for external validation. The GBM model exhibited the best performance among the five algorithms, with AUCs of 0.931 and 0.99 in the validation and test sets, respectively, and accuracies of 0.857 and 0.955 in the validation and test groups, respectively, outperforming other models. Additionally, the study found that nodule diameter and average CT value were the most significant features for predicting lung cancer infiltration using machine learning models.ConclusionThe GBM model established in this study can effectively predict the risk of infiltration in early-stage lung cancer patients, thereby improving the accuracy of lung cancer screening and facilitating timely intervention for infiltrative lung cancer patients by clinicians, leading to early diagnosis and treatment of lung cancer, and ultimately reducing lung cancer-related mortality.https://www.frontiersin.org/articles/10.3389/fpubh.2024.1368217/fullautomated machine learningpredictive modelsinfiltrative lung cancermedical image artificial intelligence recognition system (MIARS)7-TAABs |
spellingShingle | Leyuan Meng Ping Zhu Ping Zhu Kaijian Xia Kaijian Xia Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer Frontiers in Public Health automated machine learning predictive models infiltrative lung cancer medical image artificial intelligence recognition system (MIARS) 7-TAABs |
title | Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer |
title_full | Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer |
title_fullStr | Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer |
title_full_unstemmed | Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer |
title_short | Application value of the automated machine learning model based on modified CT index combined with serological indices in the early prediction of lung cancer |
title_sort | application value of the automated machine learning model based on modified ct index combined with serological indices in the early prediction of lung cancer |
topic | automated machine learning predictive models infiltrative lung cancer medical image artificial intelligence recognition system (MIARS) 7-TAABs |
url | https://www.frontiersin.org/articles/10.3389/fpubh.2024.1368217/full |
work_keys_str_mv | AT leyuanmeng applicationvalueoftheautomatedmachinelearningmodelbasedonmodifiedctindexcombinedwithserologicalindicesintheearlypredictionoflungcancer AT pingzhu applicationvalueoftheautomatedmachinelearningmodelbasedonmodifiedctindexcombinedwithserologicalindicesintheearlypredictionoflungcancer AT pingzhu applicationvalueoftheautomatedmachinelearningmodelbasedonmodifiedctindexcombinedwithserologicalindicesintheearlypredictionoflungcancer AT kaijianxia applicationvalueoftheautomatedmachinelearningmodelbasedonmodifiedctindexcombinedwithserologicalindicesintheearlypredictionoflungcancer AT kaijianxia applicationvalueoftheautomatedmachinelearningmodelbasedonmodifiedctindexcombinedwithserologicalindicesintheearlypredictionoflungcancer |